INDEX

Explanations

key objectives or purposes mentioned in the text

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

锈钢

-0.57

 Baillargeon

-0.50

 Einf

-0.48

 exce

-0.48

ÈRE

-0.46

ERON

-0.46

Solved

-0.45

mtx

-0.45

 Dage

-0.44

POSITIVE LOGITS

 InputDecoration

0.72

HideFlags

0.62

ORIGINAL

0.61

 raison

0.60

 originais

0.57

ungguhnya

0.57

basicConfig

0.56

Original

0.56

 intended

0.54

 Original

0.53

Activations Density 0.339%

key objectives or purposes mentioned in the text

No Comments

No Known Activations